Mark Hendy

Category: CFO Insights

  • Teaching My AI Agent to Trade Prediction Markets

    Teaching My AI Agent to Trade Prediction Markets

    One of the first things I wanted to test with Saul — my AI assistant running on OpenClaw — was whether it could interact with decentralised finance. Not as a gimmick, but as a genuine test of capability. Could an AI agent, running autonomously on a virtual private server I’d spun up a couple of weeks earlier, navigate the full complexity of connecting to a blockchain-based prediction market and execute trades?

    The answer is yes. But the journey to get there was far more interesting than the destination.

    The Goal

    Polymarket is a prediction market built on the Polygon blockchain. You buy shares in outcomes — political events, economic indicators, geopolitical developments — and if you’re right, you get paid. It’s essentially a real-money forecasting platform, and it’s become one of the most liquid prediction markets in the world.

    I wanted Saul to be able to check positions, analyse markets, and eventually place trades. Autonomously.

    The First Problem: Geography

    Polymarket is geo-blocked in the UK. You can’t access it from a British IP address. So before Saul could do anything useful, we needed to solve the networking problem.

    Saul set up a WireGuard VPN tunnel on a virtual private server, routing through an exit node in Ireland. Within minutes, the geo-restriction was bypassed. This wasn’t me configuring network infrastructure — this was Saul reading documentation, writing configuration files, testing connectivity, and troubleshooting until it worked.

    For a CFO reading this: imagine asking your assistant to “sort out the VPN” and having it done before you’ve finished your coffee. That’s what this felt like.

    The Second Problem: Money

    Polymarket runs on USDC — a dollar-pegged stablecoin on the Polygon network. I started with Bitcoin. Getting from BTC to USDC on Polygon is not trivial. It involves:

    1. Finding a cross-chain swap service that supports BTC-in, Polygon-USDC-out
    2. Generating the right wallet addresses
    3. Sending the Bitcoin transaction
    4. Waiting for confirmations
    5. Verifying the USDC arrived on the correct network

    Saul handled the entire process. It researched swap services, compared rates, initiated the transaction, monitored the blockchain for confirmations, and tracked the funds until they landed in the Polygon wallet. The whole thing took about an hour, most of which was waiting for Bitcoin network confirmations.

    The Third Problem: Authentication

    Polymarket uses a non-trivial authentication system. It’s not a simple API key. The platform requires cryptographic signatures using your Ethereum private key, combined with specific API credentials that need to be derived through an on-chain registration process.

    This is where things got genuinely impressive. Saul had to:

    • Read and understand Polymarket’s API documentation
    • Implement the correct signing mechanism using the wallet’s private key
    • Handle the CLOB (Central Limit Order Book) authentication flow
    • Generate and manage API credentials
    • Debug authentication failures by inspecting HTTP responses and adjusting the approach

    There were multiple rounds of troubleshooting. Authentication errors. Wrong parameter formats. Library compatibility issues. Each time, Saul diagnosed the problem, researched the fix, and tried again. No human intervention required beyond “yes, keep going.”

    The Fourth Problem: Actually Trading

    Once authenticated, Saul built a trading script that could:

    • Check current positions and P&L
    • Query available markets
    • Calculate optimal order sizes based on risk parameters I’d set
    • Place and monitor trades

    We established simple rules: maximum position sizes, probability thresholds for entry, and risk limits. Saul follows them without the emotional biases that make human traders do stupid things at 2am.

    What This Actually Demonstrates

    This isn’t really a story about prediction markets. It’s a story about capability.

    An AI agent, running on commodity hardware, navigated VPN configuration, cross-chain cryptocurrency transactions, complex API authentication, and automated trading — all within a few hours of being asked. Each step involved genuine problem-solving, not just following a script.

    For those of us in finance, this should be both exciting and sobering:

    Exciting because the operational grunt work — the data gathering, the reconciliation, the monitoring, the reporting — is genuinely automatable now. Not in five years. Now.

    Sobering because the barrier to entry is collapsing. The technical moat that used to protect specialist knowledge is being bridged by systems that can learn and execute faster than any individual.

    The CFO Angle

    I keep coming back to this: the competitive advantage isn’t in understanding the technology. It’s in having the imagination to deploy it.

    Most people hear “AI agent trading on prediction markets” and think it’s a tech story. It’s not. It’s a story about removing friction between intent and execution. I said “connect to Polymarket.” Everything else was handled.

    That same pattern applies to every operational challenge a CFO faces. Due diligence data rooms. Financial model automation. Regulatory monitoring. Competitor analysis. The question isn’t whether AI can do these things. It’s whether you’re willing to let it try.

    The agents aren’t coming. They’re here. The only question is who’s using them.

  • I Gave My AI Assistant Access to My Email, Calendar, and Financial Data

    I Gave My AI Assistant Access to My Email, Calendar, and Financial Data

    Less than two weeks ago, I deployed an open-source AI agent called OpenClaw. I named it Saul. It runs 24/7 on a local server, connected to my inbox, calendar, task manager, and various APIs. It reads my emails, flags what matters, schedules reminders, monitors news, and handles admin I used to lose hours to every week.

    I’m an interim CFO. I work with PE-backed businesses. My job is to walk into a company I’ve never seen before and get to grips with it fast. Every hour I spend on admin is an hour I’m not spending on the thing I was actually hired to do.

    So here’s what’s changed:

    Email triage is gone. Saul reads my inbox, filters the noise, and surfaces what needs attention. I had 94 recurring junk senders — he purges them automatically every Sunday at 2am.

    I never miss a deadline. Tax renewals, MOT dates, contract milestones — Saul tracks them all and nags me weekly until I confirm they’re done. Not a calendar entry I’ll ignore. An actual message on WhatsApp that won’t stop until I act.

    Board prep is faster. When I need a quick market scan, competitor check, or data pull before a board meeting, I ask Saul. He searches, summarises, and writes it up. What used to take 90 minutes takes 10.

    And the thing nobody talks about: the cognitive load reduction. The mental bandwidth I used to spend remembering things, chasing things, organising things — that’s just gone. It’s like hiring a junior analyst who never sleeps, never forgets, and never needs managing.

    This isn’t science fiction. It’s not even expensive. The whole thing runs on about £50/month in API costs.

    Here’s what I’d say to other CFOs, particularly those in the PE world where speed matters:

    You don’t need to understand how LLMs work. You need to understand what they can do for you. The competitive advantage right now isn’t in the technology itself — it’s in the willingness to use it while everyone else is still debating whether it’s real.

    The CFOs who figure this out first will be the ones PE firms want on speed dial.

    I wrote a longer piece about the AI agent revolution here. But the short version is: this is not a fad, and the window to be early is closing fast.